Commit graph

804 commits

Author SHA1 Message Date
Mario Zechner
0404a93e33 Add [Unreleased] section for next cycle 2026-02-04 14:25:32 +01:00
Mario Zechner
47a9bffcf3 Release v0.51.6 2026-02-04 14:24:49 +01:00
Mario Zechner
2135b61b93 chore: audit changelog entries 2026-02-04 14:23:55 +01:00
Mario Zechner
150aeebf7d fix(ai): respect codex baseUrl (closes #1244) 2026-02-04 12:30:31 +01:00
Mario Zechner
6cc1676eae Add [Unreleased] section for next cycle 2026-02-04 02:33:53 +01:00
Mario Zechner
5921206f9a Release v0.51.5 2026-02-04 02:33:07 +01:00
Mario Zechner
f77a1f6726 chore(changelog): note Bedrock model generation cleanup 2026-02-04 02:32:07 +01:00
Mario Zechner
1d8450ed6c
Merge pull request #1239 from unexge/push-qlzvuwsokuvn
chore(ai): clean up Bedrock-specific workarounds from `generate-models.ts`
2026-02-04 01:40:42 +01:00
Mario Zechner
2a9de37b19 Add [Unreleased] section for next cycle 2026-02-03 23:05:56 +01:00
Mario Zechner
9833717b41 Release v0.51.4 2026-02-03 23:05:07 +01:00
Burak Varlı
be1d5a0299 chore(ai): clean up Bedrock-specific workarounds from generate-models.ts
We had some workarounds in `generate-models.ts` initially - mainly to make cross-region inference work
for Amazon Bedrock provider, but now these are upstreamed into models.dev and we no longer need those.
2026-02-03 22:04:49 +00:00
Mario Zechner
c983bfdb1e Add [Unreleased] section for next cycle 2026-02-03 17:30:37 +01:00
Mario Zechner
39d719900d Release v0.51.3 2026-02-03 17:29:53 +01:00
Mario Zechner
ff5e9ec96d chore: update changelogs 2026-02-03 17:29:05 +01:00
Mario Zechner
2e1c5ebdee fix(ai): relax xhigh model check
fixes #1209
2026-02-03 13:03:46 +01:00
Mario Zechner
ff9a3f0660 Add [Unreleased] section for next cycle 2026-02-03 02:19:00 +01:00
Mario Zechner
4cbc865215 Release v0.51.2 2026-02-03 02:18:12 +01:00
Mario Zechner
0aa0b5fdba Add [Unreleased] section for next cycle 2026-02-02 19:36:52 +01:00
Mario Zechner
e02bdf8ef1 Release v0.51.1 2026-02-02 19:36:08 +01:00
Mario Zechner
59acb17354 docs: audit and update changelog entries for v0.51.0..HEAD 2026-02-02 19:35:17 +01:00
Mario Zechner
111a31e4db fix(ai): apply cache_control to string user messages 2026-02-02 19:19:12 +01:00
Mario Zechner
419c07fb19 Add [Unreleased] section for next cycle 2026-02-02 00:51:29 +01:00
Mario Zechner
580c02c74d Release v0.51.0 2026-02-02 00:50:46 +01:00
Mario Zechner
ff0eb3ecd4 fix(ai): omit strict for unsupported openai completions 2026-02-02 00:44:55 +01:00
Mario Zechner
469fb5d27c fix(ai): OAuth login/refresh now respects HTTP proxy env vars
Extracted HTTP proxy setup to shared module and imported it from both
stream.ts and oauth/index.ts. This ensures fetch() calls during OAuth
flows (token exchange, refresh, project discovery) go through the proxy.

fixes #1132
2026-02-01 19:08:13 +01:00
Mario Zechner
8f7ef85833 fix(ai): pass through cacheRetention in buildBaseOptions
fixes #1154
2026-02-01 17:37:45 +01:00
Mario Zechner
43be54c237 Add [Unreleased] section for next cycle 2026-02-01 09:36:24 +01:00
Mario Zechner
7678b075fb Release v0.50.9 2026-02-01 09:35:42 +01:00
Mario Zechner
abfd04b5c5 feat(ai): add cacheRetention stream option 2026-02-01 09:32:10 +01:00
Mario Zechner
e9ca0be769 feat(ai): add PI_AI_ANTIGRAVITY_VERSION env var override
Allows users to override the Antigravity User-Agent version when Google
updates their version requirements, avoiding the need to wait for a
package release.

Fixes #1129
2026-02-01 09:32:10 +01:00
Mario Zechner
aa83170e0f Add [Unreleased] section for next cycle 2026-02-01 02:34:06 +01:00
Mario Zechner
4baa42cb6d Release v0.50.8 2026-02-01 02:33:23 +01:00
Mario Zechner
7d632ba1c3 chore: update changelog and docs for qwen extension 2026-02-01 01:52:53 +01:00
4h9fbZ
993c45a059 feat(coding-agent): add Qwen CLI OAuth provider 2026-02-01 01:51:55 +01:00
Mario Zechner
030a61d88c feat: add maxDelayMs setting to cap server-requested retry delays
When a provider (e.g., Google Gemini CLI) requests a retry delay longer
than maxDelayMs (default: 60s), the request fails immediately with an
informative error instead of waiting silently for hours.

The error is then handled by agent-level auto-retry, which shows the
delay to the user and allows aborting with Escape.

- Add maxRetryDelayMs to StreamOptions (packages/ai)
- Add maxRetryDelayMs to AgentOptions (packages/agent)
- Add retry.maxDelayMs to settings (packages/coding-agent)
- Update _isRetryableError to match 'retry delay' errors

fixes #1123
2026-02-01 00:50:41 +01:00
Mario Zechner
f0eda2dfda Add [Unreleased] section for next cycle 2026-01-31 01:09:12 +01:00
Mario Zechner
c50a0b8b6d Release v0.50.7 2026-01-31 01:08:29 +01:00
Mario Zechner
022b20f364 Add [Unreleased] section for next cycle 2026-01-30 22:03:55 +01:00
Mario Zechner
f8d43ce02c Release v0.50.6 2026-01-30 22:03:14 +01:00
Mario Zechner
0091857f8b Add [Unreleased] section for next cycle 2026-01-30 11:48:16 +01:00
Mario Zechner
01d521c625 Release v0.50.5 2026-01-30 11:47:35 +01:00
Mario Zechner
2cee7e17de Add [Unreleased] section for next cycle 2026-01-30 03:27:09 +01:00
Mario Zechner
3f5fe42d37 Release v0.50.4 2026-01-30 03:26:23 +01:00
Mario Zechner
355bc5adc3 docs: add missing changelog entries for commits since v0.50.3
- ai: Vercel AI Gateway routing support (#1051)
- tui: Ctrl+B/Ctrl+F keybindings (#1053), character jump navigation (#1074),
  line boundary navigation (#1050), performance optimizations (#1084)
- coding-agent: set_session_name RPC (#1075), config selector folder names (#1064)
- Cross-package duplication of tui/ai changes to coding-agent
- Add New Features section to coding-agent changelog
2026-01-30 03:25:00 +01:00
Ben Vargas
e045a9f142
feat(ai): add Vercel AI Gateway routing support (#1051)
* feat(ai): add Vercel AI Gateway routing support

Add vercelGatewayRouting to OpenAICompletionsCompat, parallel to
openRouterRouting. When a model targets ai-gateway.vercel.sh and has
vercelGatewayRouting configured, the openai-completions provider passes
providerOptions.gateway with only/order in the request body.

Changes:
- types.ts: VercelGatewayRouting interface + field on OpenAICompletionsCompat
- openai-completions.ts: buildParams passes providerOptions.gateway,
  detectCompat/getCompat include the new field
- model-registry.ts: VercelGatewayRoutingSchema for models.json validation
- test: updated Required<OpenAICompletionsCompat> in test fixture

* docs(coding-agent): add vercelGatewayRouting to custom models documentation
2026-01-30 01:44:51 +01:00
Mario Zechner
8f7cdc24fd docs(ai): add changelog for tool arg defaults 2026-01-30 01:15:36 +01:00
Mario Zechner
af813f9048 fix(ai): default tool call arguments
fixes #1065
2026-01-30 01:13:16 +01:00
Mario Zechner
52532c7c00 fix(ai): update Antigravity User-Agent to 1.15.8
fixes #1079
2026-01-29 23:10:49 +01:00
Mario Zechner
df667b510a Release v0.50.3 2026-01-29 04:19:02 +01:00
Mario Zechner
87ab5c5c3b feat(ai): add Kimi For Coding provider support
- Add kimi-coding provider using Anthropic Messages API
- API endpoint: https://api.kimi.com/coding/v1
- Environment variable: KIMI_API_KEY
- Models: kimi-k2-thinking (text), k2p5 (text + image)
- Add context overflow detection pattern for Kimi errors
- Add tests for all standard test suites
2026-01-29 04:12:28 +01:00